检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Yan, Jiexuan Huang, Sheng Mu, Nankun Huangfu, Luwen Liu, Bo School of Big Data & Software Engineering Chongqing University Chongqing China College of Computer Science Chongqing University Chongqing China Fowler College of Business San Diego State University San DiegoCA United States School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (纸本)9798400706868

Real-world data consistently exhibits a long-tailed distribution, often spanning multiple categories. This complexity underscores the challenge of content comprehension, particularly in scenarios requiring Long-Tailed Multi-Label image Classification (LTMLC). In such contexts, imbalanced data distribution and multi-object recognition pose significant hurdles. To address this issue, we propose a novel and effective approach for LTMLC, termed Category-Prompt Refined Feature Learning (CPRFL), utilizing semantic correlations between different categories and decoupling category-specific visual representations for each category. Specifically, CPRFL initializes category-prompts from the pretrained CLIP's embeddings and decouples category-specific visual representations through interaction with visual features, thereby facilitating the establishment of semantic correlations between the head and tail classes. To mitigate the visual-semantic domain bias, we design a progressive Dual-Path Back-Propagation mechanism to refine the prompts by progressively incorporating context-related visual information into prompts. Simultaneously, the refinement process facilitates the progressive purification of the category-specific visual representations under the guidance of the refined prompts. Furthermore, taking into account the negative-positive sample imbalance, we adopt the Asymmetric Loss as our optimization objective to suppress negative samples across all classes and potentially enhance the head-to-tail recognition performance. We validate the effectiveness of our method on two LTMLC benchmarks and extensive experiments demonstrate the superiority of our work over *** code is available at https://***/jiexuanyan/CPRFL. © 2024 ACM.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Security Enhanced Chaotic-Map-Based Authentication Protocol for Internet of Drones

引用

IEEE Internet of Things Journal 2024年第12期11卷 22301-22309页

作者： Mahmood, Khalid Ghaffar, Zahid Farooq, Muhammad Yahya, Khalid Das, Ashok Kumar Chaudhry, Shehzad Ashraf National Yunlin University Of Science And Technology Graduate School Of Intelligent Data Science Douliu64002 Taiwan National Yunlin University Of Science And Technology Graduate School Of Engineering Science And Technology Douliu64002 Taiwan Abu Dhabi University Department Of Mathematics And Statistics College Of Arts And Sciences Abu Dhabi United Arab Emirates Istanbul Gelisim University Department Of Electrical And Electronics Engineering Istanbul34310 Turkey Sabratah University Department Of Electrical Engineering Faculty Of Engineering Regdalen Libya Center For Security Theory And Algorithmic Research Hyderabad500 032 India Abu Dhabi University Department Of Computer Science And Information Technology College Of Engineering Abu Dhabi United Arab Emirates Nisantasi University Faculty Of Engineering And Architecture Department Of Software Engineering Istanbul34398 Turkey

The Internet of Drones (IoD) extends the capabilities of unmanned aerial vehicles, enabling them to participate in a connected network. In IoD infrastructure, drones communicate not only among themselves but also with users and a control center. This interconnected communication framework holds promise for various applications, from collaborative decision-making to real-time data exchange. However, the expansion of communication in IoD also introduces new challenges, particularly in terms of security, privacy and authentication. Unfortunately, the current authentication protocols are inadequate in offering robust security features against various attacks in the IoD environment. To address these security issues and limitations, we proposed a secure protocol for the IoD environment using chaotic maps and hash functions. In addition, we also employed a physically unclonable function in the development of the proposed protocol. We assess the security of the protocol through both informal and formal security analysis. The formal security analysis is conducted through a widely used random or real (RoR) model. The informal analysis shows the rigorous security features against various attacks, such as masquerading, anonymity violation, and physical cloning attacks. Moreover, we compare the performance of the devised protocol with similar existing protocols across important performance parameters, such as communication overhead, computation overhead, and security features. The devised protocol provides a 67.86% and 17.80% reduction in computation and communication overheads, respectively, as compared to related protocols. The analysis demonstrates the proposed protocol's capacity to support secure communication in the IoD environment and satisfy desirable security attributes. © 2014 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A Multi-robot Exploration Approach for Larger Maps with Unreliable Communications

A Multi-robot Exploration Approach for Larger Maps with Unre...

引用

2022 IEEE International Conference on Unmanned Systems, ICUS 2022

作者： Wu, Lingxin Luo, Haibo College of Computer and Data Science College of Software FuZhou University Fuzhou China College of Computer and Control Engineering Minjiang University Fuzhou China

ISBN: (数字)9781665484565

ISBN: (纸本)9781665484565

The issues of limited communication distance and task capability are rarely discussed in designing multi-robot cooperative methods. However, these are important problems that cannot be avoided in practical applications. In this paper, simulation experiments are carried out on some task maps that are larger than the team's task ability. The effect of the dispersion of members on the team's task performance is tested, and the existing methods are improved by introducing long-range communication to auxiliary data sharing. At the same time, we use the calculation of Energy-Benefit to improve the task selection method based on the minimum distance to the target. Compared with existing strategies, the improved scheme performs better on communication-constrained large-map exploration tasks. © 2022 IEEE.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Applying Hybrid Clustering in Pulsar Candidate Sifting with Multi-modality for FAST Survey

引用

Research in Astronomy and Astrophysics 2024年第3期24卷 283-296页

作者： Zi-Yi You Yun-Rong Pan Zhi Ma Li Zhang Shuo Xiao Dan-Dan Zhang Shi-Jun Dang Ru-Shuang Zhao Pei Wang Ai-Jun Dong Jia-Tao Jiang Ji-Bing Leng Wei-An Li Si-Yao Li School of Physics and Electronic Science Guizhou Normal UniversityGuiyang 550025China Guizhou Provincial Key Laboratory of Radio Astronomy and Data Processing Guizhou Normal UniversityGuiyang 550025China College of Big Data and Information Engineering Guizhou UniversityGuiyang 550025China CAS Key Laboratory of FAST National Astronomical ObservatoriesChinese Academy of SciencesBeijing 100101China Key Laboratory of Information and Computing Guizhou Province Guizhou Normal UniversityGuiyang 550001China School of Big data and Computer Science Guizhou Normal UniversityGuiyang 550025China Guizhou Software Engineering Research Center Guiyang 550000China

Pulsar search is always the basis of pulsar navigation,gravitational wave detection and other research ***,the volume of pulsar candidates collected by the Five-hundred-meter Aperture Spherical radio Telescope(FAST)shows an explosive growth rate that has brought challenges for its pulsar candidate filtering ***,the multi-view heterogeneous data and class imbalance between true pulsars and non-pulsar candidates have negative effects on traditional single-modal supervised classification *** this study,a multi-modal and semi-supervised learning based on a pulsar candidate sifting algorithm is presented,which adopts a hybrid ensemble clustering scheme of density-based and partition-based methods combined with a feature-level fusion strategy for input data and a data partition strategy for *** on both High Time Resolution Universe SurveyⅡ(HTRU2)and actual FAST observation data demonstrate that the proposed algorithm could excellently identify pulsars:On HTRU2,the precision and recall rates of its parallel mode reach0.981 and 0.988 *** FAST data,those of its parallel mode reach 0.891 and 0.961,meanwhile,the running time also significantly decreases with the increment of parallel nodes within ***,we can conclude that our algorithm could be a feasible idea for large scale pulsar candidate sifting for FAST drift scan observation.

关键词： methods data analysis-surveys-methods numerical

来源：评论

学校读者我要写书评

暂无评论

FedDGL: Federated Dynamic Graph Learning for Temporal Evolution and data Heterogeneity 16

FedDGL: Federated Dynamic Graph Learning for Temporal Evolut...

引用

16th Asian Conference on Machine Learning, ACML 2024

作者： Xie, Zaipeng Li, Likun Chen, Xiangbin Yu, Hao Huang, Qian Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China College of Artificial Intelligence and Automation Hohai University Nanjing China

Federated graph learning enhances federated learning by enabling privacy-preserving collaborative training on distributed graph data. While traditional methods are effective in managing data heterogeneity, they typically assume static graph structures, overlooking the dynamic nature of real-world graphs. Integrating federated graph learning with dynamic graph neural networks addresses this issue but often fails to retain previously acquired knowledge, limiting generalization for both global and personalized models. This paper proposes FedDGL, a novel framework designed to address temporal evolution, and data heterogeneity in federated dynamic graph learning. Unlike conventional approaches, FedDGL captures temporal dynamics through a global knowledge distillation technique and manages client heterogeneity using a global prototype-based regularization method. The framework employs contrastive learning to generate global prototypes, enhancing feature representation while utilizing a prototype similarity-based personalized aggregation strategy for effective adaptation to local and global data distributions. Experiments on multiple benchmark datasets show that FedDGL achieves significant performance improvements over state-of-the-art methods, with up to 9.02% and 8.77% gains in local and global testing, respectively, compared to FedAvg. These results highlight FedDGL’s effectiveness in improving personalized and global model performance in dynamic, heterogeneous federated graph learning scenarios. © 2024 Z. Xie, L. Li, X. Chen, H. Yu & Q. Huang.

关键词： Dynamic Graph Learning Federated Graph Learning Knowledge Distillation Personalized Aggregation Prototype Learning Temporal Evolution

来源：评论

学校读者我要写书评

暂无评论

A Machine Learning-Enhanced IoT Wearable Device for Monitoring and Providing Feedback on Stuttering 3

A Machine Learning-Enhanced IoT Wearable Device for Monitori...

引用

3rd International Conference on Computational Modelling, Simulation and Optimization, ICCMSO 2024

作者： Suttarwala, Hussain Kumar, Ritesh Deorankar, Madhavi L. Daulat Sarpate, Dikshendra Shingade, Pallavi Kumar Sharma, Surender More, Vrushali Patkar, Uday Chandrakant Sharma, Deepak K. American Express Senior Software Engineer PhoenixAZ85054 United States Dr. Akhilesh Das Gupta Institute of Professional Studies Dept. of AI and Data Science Delhi New Delhi110053 India Marathwada Mitramandal College of Engineering Dept. of Electronics and Telecommunications Maharashtra Pune411052 India Zeal College of Engineering and Research Dept. of AI and Data Science MaharashtraNarhe Pune411041 India D Y Patil College of Engineering Dept. of AI and Data Science Akurdi Pune411041 India Poornima University Dept. of Electrical Engineering Jaipur India Genba Sopanrao Moze College of Engineering Dept. of AI and Data Science Balewadi Maharashtra Pune411045 India Bharati Vidyapeeth's College of Engineering Department of Computer Engineering Lavale Pune412115 India Savitribai Phule Pune University Dept. of AI and Data Science Maharashtra Pune India

ISBN: (纸本)9798350361391

This study introduces an innovative IoT-enabled wearable device tailored for monitoring and providing feedback on stuttering, leveraging advanced machine learning algorithms to enhance precision and real-time responsiveness. The device integrates an array of hardware and software elements, including sensors, microcontrollers, and communication protocols, to accurately capture speech patterns and movements. Utilizing machine learning techniques such as Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), the device performs real-time analysis to identify stuttering instances. Detailed discussions cover the criteria for selecting machine learning models, the training and testing procedures, and the metrics used for performance evaluation. The prototype underwent extensive testing and validation, showcasing high accuracy, sensitivity, and specificity in differentiating stuttered from fluent speech. User feedback emphasized the ergonomic design, user-friendly interface, and real-time feedback features, highlighting its potential to significantly enhance stuttering therapy outcomes. Comparative analysis with existing solutions revealed the device's superior performance, indicating strong potential for clinical application. The study discusses the implications for stuttering therapy, acknowledges the limitations, outlines future research directions, and underscores the device's contributions to personalized and effective stuttering interventions. This research advances the field of assistive technologies in speech therapy and demonstrates the promise of IoT-based wearable devices integrated with machine learning for improving the quality of life for individuals with stuttering disorders. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Advancements in Cybersecurity Using Deep Learning Techniques Attack Detection for Trojan Horses

Advancements in Cybersecurity Using Deep Learning Techniques...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Hosanna Princye, P. Ahila, A. Lakshmi, A. Anna Ragavendran, N. Purushothaman, K.E. Uma Maheswari, G. Saravanakumar, R. Sri Sairam College of Engineering Department of Electronics and Communication Engineering Anekal Bangalore India R.M.K. Engineering College Department of Information Technology Tamil Nadu Chennai India RMK College of Engineering and Technology Department of Artificial Intelligence and Data Science Engineering Tamil Nadu Chennai India Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India RMK College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Software Analyst Iconix Software Solution Tamil Nadu Tirunelveli India

ISBN: (纸本)9798350378092

Today's computer networks are threatened by Trojan horse assaults and other cybersecurity dangers. We propose and evaluate deep learning methods using the Kaggle-hosted Trojan Detection dataset to detect Trojan horse assaults. This project uses these approaches. Our malware detection technology uses CNN classification for accuracy. We clean and enhance the dataset to make the model more versatile. Due to extensive testing and optimization, Trojan horse detection rates reach 98.47%. We found that the deep learning architecture accurately identifies malware. We also discuss CNN model features that illuminate Trojan horse attacks. The technique offers complete cyber security and expands our knowledge of harmful software. Deep learning may boost cybersecurity defenses against emerging attacks like Trojan horses, according to our study. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Harris Hawks Optimizer with Graph Convolutional Network Based Weed Detection in Precision Agriculture

引用

Computer Systems science & engineering 2023年第8期46卷 1533-1547页

作者： Saud Yonbawi Sultan Alahmari T.Satyanarayana Murthy Padmakar Maddala E.Laxmi Lydia Seifedine Kadry Jungeun Kim Department of Software Engineering College of Computer Science and EngineeringUniversity of JeddahJeddahSaudi Arabia King Abdul Aziz City for Science and Technology RiyadhKingdom of Saudi Arabia Chaitanya Bharathi Institute of Technology HyderabadTelanganaIndia Department of Civil Engineering Vignan’s Institute of Information and Technology(A)DuvvadaVisakhapatnamAP530049India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Applied Data Science Noroff University CollegeKristiansandNorway Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityAjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblosLebanon Department of Software Kongju National UniversityCheonan31080Korea

Precision agriculture includes the optimum and adequate use of resources depending on several variables that govern crop *** agriculture offers a novel solution utilizing a systematic technique for current agricultural problems like balancing production and environmental *** control has become one of the significant problems in the agricultural *** traditional weed control,the entire field is treated uniformly by spraying the soil,a single herbicide dose,weed,and crops in the same *** more precise farming,robots could accomplish targeted weed treatment if they could specifically find the location of the dispensable plant and identify the weed *** may lessen by large margin utilization of agrochemicals on agricultural fields and favour sustainable *** study presents a Harris Hawks Optimizer with Graph Convolutional Network based Weed Detection(HHOGCN-WD)technique for Precision *** HHOGCN-WD technique mainly focuses on identifying and classifying weeds for precision *** image pre-processing,the HHOGCN-WD model utilizes a bilateral normal filter(BNF)for noise *** addition,coupled convolutional neural network(CCNet)model is utilized to derive a set of feature *** detect and classify weed,the GCN model is utilized with the HHO algorithm as a hyperparameter optimizer to improve the detection *** experimental results of the HHOGCN-WD technique are investigated under the benchmark *** results indicate the promising performance of the presented HHOGCN-WD model over other recent approaches,with increased accuracy of 99.13%.

关键词： Weed detection precision agriculture graph convolutional network harris hawks optimizer hyperparameter tuning

来源：评论

学校读者我要写书评

暂无评论

An Analysis on Cognitive Radio Adhoc Networks: Categories, Problems, and Solutions 1

引用

14th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2022, and the 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2022

作者： Vinya, Viyyapu Lokeshwari Sahithi, G. Gopal, S. Venu Rao, G. Venkateswara Shaikh, Mehwish Department of Computer Science and Engineering Vardhaman College of Engineering Telangana Shamshabad India Department of Computer Science and Engineering CVR College of Engineering Telangana Ibrahimpatnam India Department of Artificial Intelligenceand Data Science Vardhaman College of Engineering Telangana Shamshabad India Department of Computer Science and Engineering GIT GITAM-Deemed to be University A.P. Visakhapatnam India Department of Software Engineering Mehran University of Engineering and Technology Jamshoro Pakistan

ISBN: (数字)9783031275241

ISBN: (纸本)9783031275234

The exploitation of finite spectrum resources is being addressed by the new technology known as Cognitive Radio (CR). It has emerged as a potential remedy for the spectrum shortage problem in the following generation of cellular networks by utilizing opportunities in the time, frequency, and spatial domains. Many group-oriented applications that are created for CRAHN deployment have grown significantly in relevance in recent years. Multicasting is a more effective method for enabling applications that rely on group communication. In contrast to traditional wired multicast routing protocols, multicast routing for CRNs must manage a range of challenges, because of the characteristics of CRNs, such as low bandwidth, mobility, and low power. In this paper, we discussed about various types, issues and solutions for CRAHN routing, Multicast Routing, Channel Assignment and Load balancing. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Multicasting

来源：评论

学校读者我要写书评

暂无评论

Video2Reward: Generating Reward Function from Videos for Legged Robot Behavior Learning 27

Video2Reward: Generating Reward Function from Videos for Leg...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Zeng, Runhao Zhou, Dingjie Liang, Qiwei Liu, Junlin Li, Hui Huang, Changxin Li, Jianqiang Hu, Xiping Sun, Fuchun Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China College of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer Science and Technology Tsinghua University China

ISBN: (纸本)9781643685489

Learning behavior in legged robots presents a significant challenge due to its inherent instability and complex constraints. Recent research has proposed the use of a large language model (LLM) to generate reward functions in reinforcement learning, thereby replacing the need for manually designed rewards by experts. However, this approach, which relies on textual descriptions to define learning objectives, fails to achieve controllable and precise behavior learning with clear directionality. In this paper, we introduce a new video2reward method, which directly generates reward functions from videos depicting the behaviors to be mimicked and learned. Specifically, we first process videos containing the target behaviors, converting the motion information of individuals in the videos into keypoint trajectories represented as coordinates through a video2text transforming module. These trajectories are then fed into an LLM to generate the reward function, which in turn is used to train the policy. To enhance the quality of the reward function, we develop a video-assisted iterative reward refinement scheme that visually assesses the learned behaviors and provides textual feedback to the LLM. This feedback guides the LLM to continually refine the reward function, ultimately facilitating more efficient behavior learning. Experimental results on tasks involving bipedal and quadrupedal robot motion control demonstrate that our method surpasses the performance of state-of-the-art LLM-based reward generation methods by over 37.6% in terms of human normalized score. More importantly, by switching video inputs, we find our method can rapidly learn diverse motion behaviors such as walking and running. © 2024 The Authors.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：